The second application is motion segmentation, which detects groups of objects that have the same motion orientation.
Motion segmentation refers to the task of segmenting moving objects subject to their motion in order to distinguish and track them in a video.
Tong et al. [39] extracted local motion in the consecutive frames and determined the object area using the motion segmentation algorithm.
Assuming each moving object has its own trajectory in the video, the motion segmentation problem reduces to clustering the trajectories of each of the object [26], another subspace clustering problem.
In [5], a motion segmentation algorithm is proposed for extracting foreground objects with a PTZ camera.
Motion segmentation involves segregating each of the moving objects in a video sequence and is very important for robotics, video surveillance, action recognition etc.
The method presented in [36] detects objects in both images by motion segmentation and determine the vehicle distance by creating a depth map.
Optical flow-based motion segmentation uses characteristics of flow vectors of moving objects over time to detect moving regions in an image sequence.
Moreover, we expose in depth the problem of object leakage due to occlusion and highlight that motion segmentation could be treated as a graph coloring problem.
